© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52078
    Prev
    Next
    INDEX
    Explanations

    File headers or section markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rough
    -0.09
    å¸Į
    -0.09
    åĻ
    -0.09
    èĩªå·±åĸľæ¬¢
    -0.09
    èĮ«çĦ¶
    -0.08
    ä¹İ
    -0.08
    rough
    -0.08
    åĦĨ
    -0.08
     ÐĶмиÑĤÑĢ
    -0.08
    å¯Įæ°ij
    -0.08
    POSITIVE LOGITS
    lots
    0.10
    è¿Ļä¹Īå¤ļ
    0.09
    åıĶåıĶ
    0.09
    outu
    0.09
    _primitive
    0.09
    æĭĽ
    0.08
    èİ·å¾ĹæĽ´å¤ļ
    0.08
    enge
    0.08
    转载
    0.08
    /Card
    0.08
    Activations Density 0.763%

    No Known Activations